Multi-Subject Personalization
This addresses a specific challenge in creative story illustration for users of text-to-image models, representing an incremental improvement.
The paper tackles the problem of text-to-image models struggling to generate images with multiple personalized subjects without distortion or incoherent interactions, and presents Multi-Subject Personalization (MSP) which demonstrates consistent generation of good-quality images with intended subjects and interactions.
Creative story illustration requires a consistent interplay of multiple characters or objects. However, conventional text-to-image models face significant challenges while producing images featuring multiple personalized subjects. For example, they distort the subject rendering, or the text descriptions fail to render coherent subject interactions. We present Multi-Subject Personalization (MSP) to alleviate some of these challenges. We implement MSP using Stable Diffusion and assess our approach against other text-to-image models, showcasing its consistent generation of good-quality images representing intended subjects and interactions.